Progressive SIFT Matching Algorithm for Multi-Source Optical Satellite Images

Abstract

Abstract:

Considering the low matching rate of SIFT for multi-source optical satellite images, based on SIFT matching method, initial controlling points constrained by the relative scale and main orientation of SIFT features are extracted in this paper. Then, Delaunay triangulation is built by initial matching points. Local geometrical constraint model is built through point spreading. Finally, on the basis of the main orientation of features, minimum Euclidean distance criterion and local RANSAC algorithm, the matching of multi-source optical satellite images is progressively achieved with high accuracy. Compared with other matching algorithms, in the case of large scale and rotate images, the proposed algorithm has significant advantages in terms of matching amount and precision.

Key words: progressive, multi-source, SIFT, matching, point spreading

CLC Number:

P237

References

[1]Yu L, Zhang D, Holden E J.A fast and fully automatic registration approach based on point features for multi source remote sensing images[J][J].Computers & Geosciences, 2008, 34(7):838-848
[2]Wong A, Clausi D A.ARRSI: automatic registration of remote sensing images[J][J].IEEE Transactions on Geoscience and Remote Sensing, 2007, 45(5):1483-1493
[3]Lowe, D.G. Distinctive image features from scale-invariant keypoints[J].International Journal of Computer Vision, 2004, 60(2):91-110
[4]LI Xiaoming, ZHENG Lian, HU Zhanyi.SIFT Based Automatic Registration of Remotely sensed Imagery[J].Journal of Remote Sensing, 2006, 10(6):885-892
[5]YUAN Xiuxiao, LI Ran.A SIFT Image Match Method with Match-Support Measure for Multi-source Remotely Sensed Images[J].Geomatics and Information Science of Wuhan University, 2012, 37(12):1438-1442
[6] DAI Jiguang, SONG Weidong, JIA Yonghong, et al.A New Automatically Matching Algorithm for Multi-source High Resolution Optical Satellite Images[J].Acta Geodaetica et Cartographica Sinica, 2013, 42(1):80-86
[7]LV Jinjian, WEN Gongjian, LI Deren, et al.A New Method Based on Spatial Relations for Feature Matching[J].Acta Geodaetica et Cartographica Sinica, 2008, 37(3):367-373
[8]YUE Chunyu, JIANG Wanshou.An Automatic Registration Algorithm for SAR and Optical Images Based on Geometry Constraint and Improved SIFT[J].Acta Geodaetiaca et Cartographica Sinica, 2012, 41(4):570-576
[9]LI Q L, WANG G Y, LIU J G.Robust Scale- Invariant Feature Matching for Remote Sensing Image Registration[J].IEEE Geoscience and Remote Sensing Letters, 2009, 6(2):287-291
[10]ZHANG Qian, JIA Yonghong, HU Zhongwen.An Improved SIFT Algorithm for Mutli-source Remote Sensing Image Registration[J].Geometrics and Information Science of Wuhan University, 2013, 38(4):455-459
[11] JIANGS H, WANG C, XU X J, et al.Fast algorithm for multi-source image registration based on geometric feature of corners[J].Aadvanced Intelligent Computing Theories and Applicat-ions. Lecture Notes in Computer Science, 2010, 6215:438-446.
[12]ZHU Qing, WU Bo, ZHAO Jie.A Reliable Image Matching Method Based on Self-adaptive Triangle Constraint[J].CHINESE JOURNAL OF COMPUTERS, 2005, 28(10):1734-
[13]WU B, ZHANG Y, ZHU Q.A Triangulation- Based Hierarchical Image Matching Method for Wide-Baseline Images[J].Photogrammetric Engineering & Remote Sensing, 2011, 77(7):695-
[14]YANG Huachao, ZHANG Shubi, ZHANG Qiuzhao.Least Squares Matching Methods for Wide Base-l ine Stereo Images Based on SIFT Features[J].Acta Geodaetica et Cartographica Sinica, 2010, 39(2):187-194
[15]YANG Huachao, YAO Guobiao, WANG Yongbo.Dense Matching for Wide Base-line Stereo Images Based on SIFT[J].Acta Geodaetica et Cartographica Sinica, 2011, 40(5):537-543
[16]YANG Huachao, ZHANG Lei, YAO Guobiao, et al.An Automated Image Registration Method with High Accuracy Based on Local Homography Constraint[J].Acta Geodaetica et Cartographica Sinica, 2012, 41(3):401-408
[17]LI Fangfang, JIA Yonghong.李芳芳, 贾永红. 算法优化及其用于遥感影像自动配准[J].武汉大学学报:信息科学版, 2009, 34(10):1245-1249
[18] POLLARD S, PORRILL J, MAYHEW J, et al.Disparity gradient, Lipschitz continuity binocular correspondence[C]. Proceeding of Robotics Research: The Third International Symposium, Gouvieux, France, 1986:189-210.
[19] WU B, ZHANG Y, ZHU Q.Integrated Point and Edge Matching on Poor Textural Images Constrained by Self-Adaptive Triangulations[J]. Journal of Photogrammetry and Remote Sensing, 2012(68): 40- 55.
[20]Chum O.Two-view Geometry Estimation by Random Sample and Consensus[D]. Czech Technical University in Prague. PhD Thesis. 2005.
[21]ZHANG Dengrong, CAI Zhigang, YU Le.Study on Image Automatism Registration Methods Based on Matching[J].Journal of Zhejiang University: Engineering Science, 2007, 41(3):402-406